Can news predict firm bankruptcy?

Siyu Bie; Guanhao Feng; Naixin Guo; Jingyu He

doi:10.1016/j.finmar.2025.101002

Can news predict firm bankruptcy?

Siyu Bie^*
, Guanhao Feng
, Naixin Guo^*
, Jingyu He

^*Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

32 Downloads (CityUHK Scholars)

Abstract

We examine whether real-time business news predicts firm bankruptcy. Using full-text daily articles from the Dow Jones Newswires database, we generate firm-level predictors with ChatGPT and benchmark against FinBERT and dictionary-based models. ChatGPT-based variables outperform alternatives, with sentiment scores showing predictive power across horizons. Full-text news significantly enhance predictive accuracy over headlines. News-based measures add explanatory power beyond financial variables. Finally, we show that news captures timely information on macroeconomic conditions relevant to bankruptcy prediction, such as VIX, real GDP growth, and recession probability.

© 2025 The Authors

Original language	English
Article number	101002
Journal	Journal of Financial Markets
Volume	79
Online published	21 Jul 2025
DOIs	https://doi.org/10.1016/j.finmar.2025.101002
Publication status	Published - Jun 2026

Bibliographical note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Funding

He acknowledges financial support from the Hong Kong Research Grants Council (ECS21504921, GRF11507022, GRF11509224), and the Natural Science Foundation of China (NSFC72403214) and NSFC/RGC Joint Research Scheme (N_CityU105/21). Feng acknowledges financial support from the Hong Kong Research Grants Council (GRF11502721, GRF11502023) and the Natural Science Foundation of China (NSFC72203190). Bie acknowledges financial support from the National Natural Science Foundation of China (NSFC12271168). Bie, He, and Feng are partially supported by the InnoHK initiative of the Innovation and Technology Commission of the HKSAR and the Laboratory for AI-Powered Financial Technologies.

Research Keywords

Bankruptcy prediction
ChatGPT
Generative AI
News data
Sentiment

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

RGC Funding Information

RGC-funded

Access Output

10.1016/j.finmar.2025.101002

301076955.pdfFinal Published version, 3.37 MBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{273c211cd66240659e4d0ca63a878b3f,

title = "Can news predict firm bankruptcy?",

abstract = "We examine whether real-time business news predicts firm bankruptcy. Using full-text daily articles from the Dow Jones Newswires database, we generate firm-level predictors with ChatGPT and benchmark against FinBERT and dictionary-based models. ChatGPT-based variables outperform alternatives, with sentiment scores showing predictive power across horizons. Full-text news significantly enhance predictive accuracy over headlines. News-based measures add explanatory power beyond financial variables. Finally, we show that news captures timely information on macroeconomic conditions relevant to bankruptcy prediction, such as VIX, real GDP growth, and recession probability. {\textcopyright} 2025 The Authors",

keywords = "Bankruptcy prediction, ChatGPT, Generative AI, News data, Sentiment",

author = "Siyu Bie and Guanhao Feng and Naixin Guo and Jingyu He",

note = "Research Unit(s) information for this publication is provided by the author(s) concerned.",

year = "2026",

month = jun,

doi = "10.1016/j.finmar.2025.101002",

language = "English",

volume = "79",

journal = "Journal of Financial Markets",